How to use GitHub Copilot Agent Skills in Visual Studio

With the introduction of agent skills, we can teach our AI agent to handle our most repetitive and specialized workflows. After adding context through an agent.md file, integrating tool calls using MCP, creating our own Agents, this is a logical next step in defining your AI enabled software development lifecycle.

Here's everything you need to know to get started.

What are agent skills?

Agent skills are folders of instructions, scripts, and resources that GitHub Copilot can load automatically when relevant to your prompt. Think of them as reusable "playbooks" you write once and invoke repeatedly — without having to re-explain the context every time.

Unlike custom instructions, which set broad coding guidelines that apply across nearly every task, skills are meant for specialized, on-demand capabilities: things like running a specific test suite, converting file formats, generating components, or following a custom deployment checklist.

How to create your first skill

Skills follow an open standard, which means they work across multiple AI tools and IDE’s.

Skills location

Skills live in a dedicated directory. You have two placement options:

Project-scoped skills (specific to one repository):

.github/skills/
.claude/skills/
.agents/skills/

Personal skills (shared across all your projects):

~/.copilot/skills/
~/.agents/skills/

Remark: Visual Studio 2026 discovers skills from all of these locations automatically.

Skill structure

Each skill is a folder containing at minimum a SKILL.md file. This file uses YAML frontmatter to describe the skill and a Markdown body to provide instructions.

Here's a minimal example — a skill that formats code comments according to your team's style:

.github/skills/
  comment-formatter/
    SKILL.md
    examples/
      before.js
      after.js

And the SKILL.md itself:

---
name: comment-formatter
description: Formats inline code comments to match our team's documentation style guide.
---

When asked to clean up or format comments in a file, follow these rules:

1. Use JSDoc-style block comments for all functions.
2. Write in present tense ("Returns the user object", not "Return...").
3. Keep lines under 80 characters.
4. Reference the examples in `examples/before.js` and `examples/after.js` to calibrate style.

Once your skill is in place, Copilot discovers it automatically. There are two ways to use it:

Let Copilot decide: When you type a relevant prompt like "clean up comments in this file," Copilot matches it against your skill's description and loads the skill automatically.
Invoke manually: Type /comment-formatter in the chat to trigger it directly. You can also add extra context: /comment-formatter for the auth module.

Using community skills

You don't have to write every skill from scratch. There are multiple great sources for pre-built skills:

github/awesome-copilot — a growing community collection covering a wide range of tasks
anthropics/skills — reference skills from Anthropic, also compatible with Claude Code
skills.sh — a long list of skills from multiple sources

You can install them using the GitHub CLI:

gh skill install <repo>/<skill-name>

or when using a skill from skills.sh:

npx skills add <owner/repo>

Always review a skill's contents before installing it, especially if it includes scripts with bash in allowed-tools.

Skills in Visual Studio 2026

If you're on Visual Studio 2026, Agent Skills were added in the March 2026 update. The experience is largely the same:

Place your skills in .github/skills/, .claude/skills/, or .agents/skills/ in your repository.
Visual Studio discovers them automatically.
Skills appear in the Tools window alongside any installed MCP servers:

Once your skill is in place, Copilot discovers it automatically. From that moment on, the Copilot Agent can decide to use this skill when appropriate. When a skill is active, it appears in the chat so you know it's being applied.

I couldn’t find a way to manually invoke a skill, but I hope that is a feature that will be added in the future.

Wrapping up

Agent Skills represent a meaningful shift in how developers can work with GitHub Copilot. Rather than relying on a one-size-fits-all AI, you can now build a library of application specific capabilities that grow with your team and your codebase. Whether you're automating a deployment checklist, enforcing a documentation format, or wiring up a custom conversion pipeline, skills give you a structured, repeatable, and portable way to get there.

I'm happy to see that there are finding their way also in Visual Studio. So, no excuse to not use it!

My recommendation: start small.

Pick one repetitive task you do every week and write a skill for it. The investment is minimal, and the payoff compounds over time.

More information

Manage agent skills with GitHub CLI - GitHub Changelog

Use Agent Skills with GitHub Copilot - Visual Studio (Windows) | Microsoft Learn

How I built a custom agent skill to configure Application Insights

VS Code Planning mode

After the introduction of Plan mode in Visual Studio , it now also found its way into VS Code. Planning mode, or as I like to call it 'Hannibal mode', extends GitHub Copilot's Agent Mode capabilities to handle larger, multi-step coding tasks with a structured approach. Instead of jumping straight into code generation, Planning mode creates a detailed execution plan. If you want more details, have a look at my previous post . Putting plan mode into action VS Code takes a different approach compared to Visual Studio when using plan mode. Instead of a configuration setting that you can activate but have limited control over, planning is available as a separate chat mode/agent: I like this approach better than how Visual Studio does it as you have explicit control when plan mode is activated. Instead of immediately diving into execution, the plan agent creates a plan and asks some follow up questions: You can further edit the plan by clicking on ‘Open in Editor’: ...

The art of simplicity

Search This Blog